Upload tokenizer_config.json with huggingface_hub

tokenizer_config.json

@@ -17,72 +17,51 @@
     "<|video|>"
   ],
   "image_token": "<|image|>",
-  "is_local": true,
   "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
-  "model_specific_special_tokens": {
-    "audio_token": "<|audio|>",
-    "boa_token": "<|audio>",
-    "boi_token": "<|image>",
-    "eoa_token": "<audio|>",
-    "eoc_token": "<channel|>",
-    "eoi_token": "<image|>",
-    "eot_token": "<turn|>",
-    "escape_token": "<|\"|>",
-    "etc_token": "<tool_call|>",
-    "etd_token": "<tool|>",
-    "etr_token": "<tool_response|>",
-    "image_token": "<|image|>",
-    "soc_token": "<|channel>",
-    "sot_token": "<|turn>",
-    "stc_token": "<|tool_call>",
-    "std_token": "<|tool>",
-    "str_token": "<|tool_response>",
-    "think_token": "<|think|>"
-  },
-  "pad_token": "<eos>",
+  "pad_token": "<pad>",
   "padding_side": "left",
   "processor_class": "Gemma4Processor",
   "response_schema": {
+    "type": "object",
     "properties": {
       "role": {
         "const": "assistant"
       },
       "thinking": {
-        "type": "string",
-        "x-regex": "<\\|channel\\>(?:thought\\n)?(.+?)<channel\\|>"
+        "type": "string"
+      },
+      "content": {
+        "type": "string"
       },
       "tool_calls": {
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>",
+        "type": "array",
         "items": {
+          "type": "object",
           "properties": {
+            "type": {
+              "const": "function"
+            },
             "function": {
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})",
               "properties": {
-                "arguments": {
-                  "type": "string",
-                  "x-mapping-regex": {
-                    "(\\{|,)\\s*([a-zA-Z_]\\w+):": "\\1\"\\2\":",
-                    "<\\|\\\"\\|>": "\""
-                  },
-                  "x-regex": "call:[^{]+(\\{.*\\})"
-                },
                 "name": {
-                  "type": "string",
-                  "x-regex": "call:([^{]+)"
+                  "type": "string"
+                },
+                "arguments": {
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call",
+                  "additionalProperties": {}
                 }
-              },
-              "type": "object"
-            },
-            "type": {
-              "const": "function"
+              }
             }
-          },
-          "type": "object"
-        },
-        "type": "array",
-        "x-regex-iterator": "<\\|tool_call\\>(.*?)<tool_call\\|>"
+          }
+        }
       }
     },
-    "type": "object"
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<content>(?:(?!\\<\\|tool_call\\>)(?!\\<turn\\|\\>).)+)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?:\\<turn\\|\\>)?"
   },
   "soc_token": "<|channel>",
   "sot_token": "<|turn>",